Article
Computer Science, Software Engineering
Tanghuai Fan, Zhanfeng Yao, Longzhe Han, Baohong Liu, Li Lv
Summary: The DPC algorithm performs poorly on complex data sets with large differences in density, flow pattern or cross-winding, and has relatively poor fault tolerance in sample allocation. This article proposes the DPC-KNNS algorithm to improve clustering performance on datasets with large density differences and complex patterns.
CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE
(2021)
Article
Automation & Control Systems
J. A. Romero-del-Castillo, Manuel Mendoza-Hurtado, Domingo Ortiz-Boyer, Nicolas Garcia-Pedrajas
Summary: Multi-label learning is an important field in machine learning research, and the multi-label k-nearest neighbor method is one of the most successful algorithms. However, allocating the appropriate value of k is a challenge in difficult classification tasks, as different regions may require different k values. We propose a simple yet powerful method to set local k values, obtaining the optimal value by optimizing the local effect of different k values near each prototype.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2022)
Article
Computer Science, Artificial Intelligence
Maximiliano Cubillos, Sanne Wohlk, Jesper N. Wulff
Summary: This study proposes a bi-objective algorithm based on the k-nearest neighbors method for imputing missing values in data with continuous variables and multilevel structures. Results from simulation studies show that the proposed method outperforms benchmark methods in cases with high intraclass correlation, reducing estimation bias and coefficient of determination.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Computer Science, Artificial Intelligence
Danny Hartanto Djarum, Zainal Ahmad, Jie Zhang
Summary: RBOSR is a new approach that improves the performance and efficiency of the PM2.5 stacked model. It significantly reduces training time and outperforms the original model.
APPLIED SOFT COMPUTING
(2023)
Article
Computer Science, Artificial Intelligence
Yongda Cai, Joshua Zhexue Huang, Jianfei Yin
Summary: This paper proposes a new method called adaptive k-nearest neighbors similarity graph (AKNNG) for constructing a better graph structure. By assigning different k values to different data points and automatically adjusting the k value based on the similarity graph, the AKNNG method improves clustering accuracies and reduces construction time.
Article
Computer Science, Artificial Intelligence
Peter Muellner, Elisabeth Lex, Markus Schedl, Dominik Kowald
Summary: In this study, we propose a novel differentially private KNN-based recommender system called ReuseKNN, which reduces privacy risk by identifying highly reusable neighborhoods with small size. Experimental results demonstrate that ReuseKNN outperforms traditional UserKNN in terms of accuracy while protecting a smaller number of neighbors with differential privacy.
ACM TRANSACTIONS ON INTELLIGENT SYSTEMS AND TECHNOLOGY
(2023)
Article
Computer Science, Artificial Intelligence
Zhibin Pan, Yiwei Pan, Yidi Wang, Wei Wang
Summary: The LMKNN classifier has better performance and robustness compared to the KNN classifier, but the unreliable nearest neighbor selection rule and single local mean vector strategy severely impact its classification performance.
Article
Green & Sustainable Science & Technology
Xinran Li, Wei Wang, Hao Gu
Summary: Electric vehicles have the potential to improve environmental sustainability, but the current charging infrastructures cannot keep up with the increasing demand. Sharing private charge posts during idle time is a proactive solution that benefits both charge post owners and non-owner EV drivers. To create a trusted environment, a blockchain-enabled sharing charging system with redesigned procedures and a non-myopic charge post match strategy is proposed. Test results on Ethereum show that the redesigned system can provide high quality services with affordable computational resource consumption and improve the overall matching successful rate of charging requests.
JOURNAL OF CLEANER PRODUCTION
(2023)
Article
Environmental Sciences
Xinpu Liu, Yanxin Ma, Ke Xu, Ling Wang, Jianwei Wan
Summary: This paper proposes a keypoints-aligned siamese network for completing partial TLS point clouds, which learns prior geometric information of complete shapes and establishes long-range geometric relationships, resulting in improved point cloud completion.
Article
Computer Science, Information Systems
Shanshan Liu, Pedro Reviriego, Jose Alberto Hernandez, Fabrizio Lombardi
Summary: This paper explores how to provide protection and error tolerance for classifiers by exploiting the algorithmic properties, applied to the k Nearest Neighbors classifier, and proposes a time-based modular redundancy scheme to reduce the number of re-computations needed effectively.
IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTING
(2021)
Article
Computer Science, Hardware & Architecture
Payam Bahrani, Behrouz Minaei-Bidgoli, Hamid Parvin, Mitra Mirzarezaee, Ahmad Keshavarz
Summary: Despite advancements in recommender systems, there is still room for improvement. This study developed an improved method using weighted averaging and a Gaussian mixture model, which showed more accurate results and faster execution time compared to traditional methods.
JOURNAL OF SUPERCOMPUTING
(2023)
Article
Computer Science, Information Systems
Jiawei Yang, Yu Chen, Sylwan Rahardja
Summary: Traditional outlier detectors have neglected the group-level factor in calculating outlier scores for objects in data, resulting in the inability to capture collective outliers. To address this issue, a framework called neighborhood representative (NR) is proposed, enabling existing outlier detectors to efficiently detect outliers, including collective outliers, while maintaining computational integrity. By selecting representative objects, scoring them, and applying the score to collective objects, NR achieves this without altering existing detectors. NR is compatible with existing detectors and improves performance on eleven real-world datasets by an average of 8% (0.72 to 0.78 AUC) relative to twelve state-of-the-art outlier detectors. The implementation of NR can be found at www.OutlierNet.com for reproducibility. (c) 2022 The Author(s). Published by Elsevier Inc. This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/).
INFORMATION SCIENCES
(2023)
Article
Statistics & Probability
Emre Demirkaya, Yingying Fan, Lan Gao, Jinchi Lv, Patrick Vossler, Jingbo Wang
Summary: This work introduces a novel two-scale DNN method by linearly combining two DNN estimators with different subsampling scales to reduce bias and achieve the optimal nonparametric convergence rate under the fourth-order smoothness condition.
JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION
(2022)
Article
Mathematics
Dusan Herich, Jan Vascak, Iveta Zolotova, Alexander Brecko
Summary: This study explores the use of edge-enabled cloud computing in unmanned aerial vehicles for autonomous control, focusing on developing an effective strategy for task offloading. By utilizing a network evaluation method based on mean opinion score metrics and machine learning algorithms for path length prediction, the system evaluates computational complexity and makes offloading decisions based on network metrics and solution depth prediction. The proposed system, applied to the A* path planning algorithm, demonstrates up to 94% accuracy in offloading decisions.
Article
Computer Science, Information Systems
Junnan Li, Qingsheng Zhu, Quanwang Wu, Zhu Fan
Summary: Class imbalance is a significant factor leading to performance deterioration in classifiers. Techniques such as SMOTE and its extension, NaNSMOTE, have been successful in addressing this issue and have been proven effective on real data sets.
INFORMATION SCIENCES
(2021)
Article
Engineering, Industrial
Zonggui Tian, Ray Y. Zhong, Ali Vatankhah Barenji, Y. T. Wang, Zhi Li, Yiming Rong
Summary: Urbanisation and changing consumer demands pose challenges to improve customer satisfaction in urban logistics. Current satisfaction evaluations are time-consuming and lack transparency. A blockchain-based approach with machine learning is proposed to predict satisfaction and enhance transparency in the industry.
INTERNATIONAL JOURNAL OF PRODUCTION RESEARCH
(2021)
Article
Computer Science, Artificial Intelligence
Mingxing Li, Ray Y. Zhong, Ting Qu, George Q. Huang
Summary: Cyber-physical systems (CPS) hold great potential in smart manufacturing, but the complexity and uncertainty of manufacturing optimization remain a challenge. This paper introduces a novel divide and conquer approach, Spatial-Temporal Out-Of-Order execution (ST-OOO), to decompose the complex optimization problem into smaller subproblems and generate a global solution through rolling spatiotemporal execution.
JOURNAL OF INTELLIGENT MANUFACTURING
(2022)
Article
Computer Science, Interdisciplinary Applications
Ali Vatankhah Barenji, Hanyang Guo, Yitong Wang, Zhi Li, Yiming Rong
Summary: Successful global manufacturing enterprises require great collaboration among designers, manufacturers, and customers, while achieving trustable collaboration and efficiently utilizing customer views remains a challenge.
ROBOTICS AND COMPUTER-INTEGRATED MANUFACTURING
(2021)
Article
Computer Science, Interdisciplinary Applications
Zhiheng Zhao, Leidi Shen, Chen Yang, Wei Wu, Mengdi Zhang, George Q. Huang
Summary: Modern warehousing systems for fresh and cold-keeping storage have complex operation procedures, accelerated pace, and high labour intensity, leading to hazardous working environments. This paper introduces an IoT and digital twin-enabled tracking solution framework for safety management, with an indoor safety tracking mechanism developed for real-time precise location information. A case study demonstrates the feasibility and effectiveness of the proposed techniques, showing high accuracy in detecting abnormal behavior and ensuring long-term use through adaptation.
COMPUTERS & OPERATIONS RESEARCH
(2021)
Article
Computer Science, Interdisciplinary Applications
Zhiheng Zhao, Ray Y. Zhong, Yong-Hong Kuo, Yelin Fu, G. Q. Huang
Summary: iGather is a novel cyber-physical architecture for spatial temporal analytics that traces COVID-19 indirect contacts through digital chromosomes, representing human activity instances in the physical world. The deployment of physical hardware and spatial temporal analytics has shown high spatial temporal correlation and indirect tracing capabilities, confirmed through testing in various spatial temporal correlated cases.
INDUSTRIAL MANAGEMENT & DATA SYSTEMS
(2021)
Article
Engineering, Industrial
Xiang T. R. Kong, Miaohui Zhu, Yu Liu, Kaida Qin, George Q. Huang
Summary: This paper introduces an order batching approach based on an automated system to minimize the processing time and system response time of auction orders. The proposed method achieves better efficiency in order processing according to computational experiments.
INTERNATIONAL JOURNAL OF PRODUCTION RESEARCH
(2023)
Article
Engineering, Industrial
Bill Wang, Zhiyu Lin, Michael Wang, Fangyi Wang, Peng Xiangli, Zhi Li
Summary: This research develops a system architecture of blockchain-based multi-tier sustainable supply chain management in the PPE industry, aiming to address the challenges faced in managing multi-tier suppliers and ensuring compliance with production, social, and environmental standards. The architecture is validated through theoretical basis, expert opinions, and technical solutions.
INTERNATIONAL JOURNAL OF PRODUCTION RESEARCH
(2023)
Article
Energy & Fuels
Changping Zhao, Juanjuan Sun, Yu Gong, Zhi Li, Peter Zhou
Summary: This paper proposes a blockchain-based blue carbon trading management system, utilizing the advantages of decentralization, high transparency, and non-tamperability to achieve efficient, low-cost, and intelligent blue carbon trading.
Article
Chemistry, Analytical
Ali Barenji, Benoit Montreuil
Summary: The digitalization and adoption of advanced technologies in supply chain and logistics have changed the business model and introduced new avenues concerning supply chain 4.0. However, the lack of a secure, trustworthy, and open sharing platform hinders companies from relying on sharing economics. To address this issue, this paper presents a blockchain-enabled hyperconnected logistics platform that aims to improve trust-ability, openness, and interoperability in supply chain 4.0.
Article
Computer Science, Artificial Intelligence
Jian Ni, Yue Xu, Zhi Li, Jun Zhao
Summary: The motivation of this study is to investigate the use of three promising types of recurrent neural networks (RNNs) for copper price prediction. The results show that RNN models with memory units outperform memory-free ANN models, and longer input window lengths may not necessarily result in better prediction performance. By combining two RNNs (LSTM and BiLSTM) with shorter input window lengths using a simpler averaging approach, the best ensemble prediction model can be obtained.
Article
Computer Science, Artificial Intelligence
Shiquan Ling, Daqiang Guo, Mingxing Li, Yiming Rong, George Q. Huang
Summary: An assembly cell line (ACL) is a type of cell production practice that was derived from the Toyota Production System and has been rapidly adopted in various industries. It allows workers to perform multiple tasks throughout the entire product assembly process by dividing the conveyor line into assembly cells. However, the lack of real-time information sharing makes it difficult to coordinate the capacities of different assembly cells in complex manufacturing environments. To address this issue, this paper proposes a smart ACL system that uses artificial intelligence and IoT technologies to synchronize demand and capacity, improving production efficiency.
JOURNAL OF INTELLIGENT MANUFACTURING
(2022)
Article
Computer Science, Interdisciplinary Applications
S. Y. Wang, George Q. Huang
Summary: In an Industry 4.0 Factory, physical entities are digitized into digital twins with smart IoT devices, resulting in Cyber-Physical Production Systems (CPPS). Real-time data analytics provides traceability and visibility in both the physical and cyber domains. This paper introduces the concept of cyber-physical inventory, or meta-inventory, to Industry 4.0 CPPS. The use of meta-inventory can reduce complexity and uncertainties, and achieve resilience without incurring holding costs.
ROBOTICS AND COMPUTER-INTEGRATED MANUFACTURING
(2023)
Article
Computer Science, Interdisciplinary Applications
Arjun Rachana Harish, X. L. Liu, Ming Li, Ray Y. Zhong, George Q. Huang
Summary: E-commerce logistics financing drives growth in small and medium-sized logistics companies, but faces challenges in information asymmetry, hidden centrality, and information ownership opaqueness. Blockchain technology is considered promising to address these concerns through shared ledger, smart contracts, and tokens. This study introduces a blockchain-enabled cyberphysical traceability system for logistics financing based on digital asset tokenization, bringing visibility and traceability to supply chain transactions. The system's design and implementation are presented, along with its application in logistics financing, which offers resolution and reduced upfront expenditure for stakeholders.
COMPUTERS IN INDUSTRY
(2023)
Article
Green & Sustainable Science & Technology
Max Cichocki, Ali V. Barenji, Benoit Montreuil, Christian Landschuetzer
Summary: This study aims to develop a hyperconnected logistic platform for heavy-duty machinery in the composting industry, integrating physical, digital, and operational connections. The proposed architecture consists of four layers: the Domain Model, the MBSE Model, the Information Sharing Model, and the Agent-based Simulation Platform. The feasibility of the architecture is demonstrated through a use case, showing the success of the hyperconnected platform in serving composting facilities and promoting high-quality compost production. This effort contributes to the realization of the Physical Internet vision and the enhancement of the circular economy in the composting sector.
Proceedings Paper
Computer Science, Information Systems
Mingxing Li, Daqiang Guo, George Q. Huang
Summary: The widespread adoption of Industry 4.0 technologies in factories is transforming manufacturing operations management. Real-time data are acknowledged as beneficial for this management, and utilizing these data to facilitate production and intralogistics operations is an emerging challenge. This study proposes the concept of operation twins for achieving synchronized PiL operations based on three dimensions of synchronization.
ADVANCES IN PRODUCTION MANAGEMENT SYSTEMS: ARTIFICIAL INTELLIGENCE FOR SUSTAINABLE AND RESILIENT PRODUCTION SYSTEMS, PT V
(2021)
